Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    instances of human suffering and atrocities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    StoryboardSegue
    -0.57
    }{*}{}
    -0.43
     distracting
    -0.42
    RegistryLite
    -0.40
     distraction
    -0.40
     Überras
    -0.39
    fassungs
    -0.39
     distractions
    -0.38
     distract
    -0.38
     neutralized
    -0.38
    POSITIVE LOGITS
     abuse
    1.56
     torture
    1.55
     tort
    1.34
    tort
    1.32
     abuses
    1.28
     tortura
    1.28
    abuse
    1.27
    Abuse
    1.25
     Abuse
    1.25
     abused
    1.24
    Act Density 0.813%

    No Known Activations